Published June 29, 2020 | Version v1
Report Open

Detecting and Localizing Leakage Hotspots in Water Distribution Networks via Regularization of an Inverse Problem: An Application to the Battle of Leakage Detection and Isolation Methods 2020 Competition

  • 1. InfraSense Labs, Department of Civil and Environmental Engineering, Imperial College, London, UK


The application of a model-based leak localization method on the data set provided for the Battle of Leakage Detection and Isolation Methods 2020 is investigated. First, an analysis of flow residuals is used to detect a possible leak event which is then confirmed or rejected by the model-based leak localization. A prior clustering of daily flow profiles results in the identification of possible leak days, and leak-free days, in the entire data set.


The project was co-funded by Cla-Val UK Ltd



Files (309.6 kB)

Name Size Download all
309.6 kB Preview Download

Additional details


Dynamically Adaptive and Resilient Water Supply Networks for a Sustainable Future EP/P004229/1
UK Research and Innovation
EPSRC Centre for Doctoral Training in Sustainable Civil Engineering EP/L016826/1
UK Research and Innovation